Differentially Private Algorithms for Synthetic Power System Datasets

TL;DR

This paper introduces differentially private algorithms to generate synthetic power system datasets that maintain data utility for specific models while ensuring privacy, addressing security concerns in data sharing.

Contribution

It presents novel privacy-preserving algorithms using Laplace and Exponential mechanisms combined with convex optimization for synthetic power system data generation.

Findings

Algorithms effectively preserve data accuracy for downstream tasks.

Synthetic datasets protect privacy of real network parameters.

Applicable to wind power data and network parameters.

Abstract

While power systems research relies on the availability of real-world network datasets, data owners (e.g., system operators) are hesitant to share data due to security and privacy risks. To control these risks, we develop privacy-preserving algorithms for the synthetic generation of optimization and machine learning datasets. Taking a real-world dataset as input, the algorithms output its noisy, synthetic version, which preserves the accuracy of the real data on a specific downstream model or even a large population of those. We control the privacy loss using Laplace and Exponential mechanisms of differential privacy and preserve data accuracy using a post-processing convex optimization. We apply the algorithms to generate synthetic network parameters and wind power data.